JP5325337B2 - Surveillance camera terminal - Google Patents

Abstract

A surveillance camera terminal (1) is provided which is capable of lowering the possibility of losing sight of an object being tracked at the time of handover of the object to another surveillance camera terminal (1). The surveillance camera terminal (1) changes the imaging visual field of the imaging section (12) by using an object person as a reference when the object person is not positioned near a handover area between the surveillance camera terminal (1) and another surveillance camera terminal (1) located adjacent thereto. When the object person is positioned near the handover area between the surveillance camera terminal (1) and the adjacent surveillance camera terminal (1), the surveillance camera terminal (1) changes the imaging visual field of the imaging section (12) by using an imaging visual field for use in handover as a reference. Therefore, the imaging visual field of the imaging section (12) has already been adjusted to the imaging visual field for use in handover at the time when the object person enters the handover area.

Description

  The present invention relates to a surveillance camera terminal used in a wide area monitoring system that tracks a suspicious person over a wide area at a place where an unspecified number of people gather, such as a station, a shopping center, and a downtown area.

  Conventionally, in places where a large number of unspecified people gather, such as stations, shopping centers, and downtowns, a person such as a suspicious person who took a peculiar action using a plurality of surveillance camera terminals (hereinafter simply referred to as a tracking target person). .) And a wide area monitoring system that tracks the detected person to be tracked. In addition, in order to reduce the number of surveillance camera terminals used in the entire system and reduce the cost of system construction, each surveillance camera uses a surveillance camera terminal that changes the imaging field of view according to the movement of the person being tracked. A monitoring target area allocated to a terminal is increased (see Patent Document 1).

JP 2006-310901 A

  However, in the conventional general wide-area monitoring system, the monitoring camera terminal changes the imaging field of view so that the tracking target person is imaged at the center of the frame image. That is, the surveillance camera terminal changes the imaging field of view with reference to the tracking target person.

  In addition, when a tracking target person who is tracking enters a delivery area defined with another monitoring camera terminal, the monitoring camera terminal (hereinafter referred to as a delivery side of the monitoring camera terminal) is tracking the tracking target person. This is called a surveillance camera terminal.) Sends a delivery request. This delivery request is transmitted to another surveillance camera terminal (hereinafter referred to as the takeover-side surveillance camera terminal) that takes over the tracking of the tracking subject.

  The handover-side monitoring camera terminal changes the imaging field of view to the imaging field of view when delivering the tracking target person defined with the delivery-side monitoring camera terminal. In addition, the monitoring camera terminal on the delivery side also changes to the imaging field of view when the tracking target person defined with the monitoring camera terminal on the takeover side is delivered. Then, both the delivery side surveillance camera terminal and the takeover side surveillance camera terminal image the delivery area at substantially the same timing. The monitoring camera terminal on the takeover side identifies the tracking target person tracked by the monitoring camera terminal on the delivery side from the persons imaged in the frame image obtained by imaging the delivery area. The monitoring camera terminal on the takeover side takes over the tracking of the identified tracking target person. The tracking target person is identified based on the position of the person including the tracking target person in the frame image captured by each surveillance camera terminal.

  Thus, after the tracking target person enters the delivery area, both the monitoring camera terminal on the delivery side and the surveillance camera terminal on the takeover side match the imaging field of view with the imaging field of view when the tracking target person is delivered. It was. For this reason, when these surveillance camera terminals synchronously image the transfer area, the tracking target person may have already moved out of the transfer area. In this case, the person to be tracked is lost and tracking of the person to be tracked fails.

  An object of the present invention is to provide a surveillance camera terminal that can suppress losing sight of the tracked object when the tracked object being tracked is delivered to another surveillance camera terminal.

  In order to achieve the above object, the surveillance camera terminal of the present invention is configured as follows.

  The imaging visual field control means changes the imaging visual field of the imaging means within the monitoring target area. The tracking target extraction unit processes the frame image captured by the imaging unit within the imaging field of view, and extracts the tracking target being captured. The tracking unit detects the position of the tracking target in the monitoring target area based on the position on the frame image of the tracking target extracted by the tracking target extraction unit and the imaging field of view of the imaging unit, and tracks the tracking target. The tracking unit tracks the tracking target based on a change in the position of the tracking target in the monitoring target area with time, which is obtained by processing the frame images in time series. The imaging visual field control means changes the imaging visual field of the imaging means according to the position in the monitoring target area of the tracking target tracked by the tracking means. For example, the imaging field of view of the imaging unit is changed so that the tracking target is imaged in the approximate center of the frame image. Further, by using the movement vector of the tracking target obtained from the tracking result of the tracking target in the tracking unit, it is possible to change the imaging field of view while predicting the position of the tracking target.

  The imaging visual field storage means stores the imaging visual field when the tracking target is transferred for each other monitoring camera terminal that transfers the tracking target. The detecting means detects whether or not the tracking target tracked by the tracking means has moved to the vicinity of the delivery area with another monitoring camera terminal. The detection means may be configured to detect, for example, whether the tracking means has moved around the transfer area with another monitoring camera terminal, based on the imaging field of view of the imaging means, or the position of the tracking target being tracked by the tracking means Thus, it may be configured to detect whether or not it has moved to the vicinity of the delivery area with another surveillance camera terminal. Further, a predetermined mark is painted around the delivery area, and whether or not the tracking unit has moved to the vicinity of the delivery area with another monitoring camera terminal is detected based on whether or not the predetermined mark has been detected from the frame image. It is good also as a structure.

  The imaging field control unit stores the imaging field of the imaging unit in the imaging field storage unit when the detection unit detects that the tracking target tracked by the tracking unit has moved to the vicinity of the transfer area with another monitoring camera terminal. It matches with the imaging field of view when handing over the tracking target to the other surveillance camera terminal. At this time, the imaging visual field control means switches the imaging visual field of the imaging means without causing the tracking target person to be tracked out of the frame, and the imaging visual field storage means stores the imaging visual field of the imaging means without losing sight of the tracking target person. It is preferable to match with the delivery area with the other surveillance camera terminal stored in the.

  In addition, when the detection means detects that the tracking target being tracked by the tracking means has moved to the vicinity of the delivery area with another monitoring camera terminal, the tracking target is delivered to another monitoring camera terminal that delivers the tracking target. The delivery request may be made. In response to this request, the monitoring camera terminal on the other side that delivers the tracking target may be configured to change the imaging field of view to the imaging field of view that delivers.

  As a result, when the tracking target person enters the delivery area, the imaging field of view of both the monitoring camera terminal on the delivery side and the monitoring camera terminal on the takeover side is the imaging field of view when delivering the tracking target. . That is, there is no time required for these surveillance camera terminals to change the imaging field of view from the entry of the tracking target person into the delivery area to the imaging field of view when the tracking target person is delivered. Accordingly, it is possible to suppress losing sight of the tracking target when the tracking target being tracked is transferred to another monitoring camera terminal.

  According to the present invention, it is possible to suppress losing sight of a tracking target when the tracking target being tracked is transferred to or from another surveillance camera terminal.

It is the schematic which shows the structure of a wide area monitoring system. It is a block diagram which shows the structure of the principal part of a surveillance camera terminal. It is a figure explaining the monitoring object area and imaging area in a surveillance camera terminal. It is a figure which shows the relationship of the monitoring object area between adjacent monitoring camera terminals. It is a flowchart which shows operation | movement of a surveillance camera terminal. It is a flowchart which shows a tracking process. It is a figure which shows the captured image at the time of a tracking process. It is a flowchart which shows a takeover process.

  Hereinafter, a surveillance camera terminal according to an embodiment of the present invention will be described.

  FIG. 1 is a schematic diagram showing a configuration of a wide area monitoring system using a monitoring camera terminal according to an embodiment of the present invention. This wide area monitoring system is a network system having a plurality of monitoring camera terminals 1 (1A to 1H). This wide area monitoring system is, for example, an ad hoc network system. Data communication can be performed between the monitoring camera terminals 1 directly or via another monitoring camera terminal 1. The data communication between the monitoring camera terminals 1 may be wireless or wired.

  Note that the number of monitoring camera terminals 1 constituting the wide area monitoring system is not limited to the eight illustrated here, and may be any number as long as it is a plurality. Moreover, the line which connects between the monitoring camera terminals 1 shown in FIG. 1 is a link. Moreover, in the following description, when it demonstrates without distinguishing especially the monitoring camera terminals 1A-1H, it shows with the monitoring camera terminal 1. FIG.

  FIG. 2 is a diagram illustrating a configuration of a main part of the monitoring camera terminal. The surveillance camera terminal 1 includes a control unit 11, an imaging unit 12, a drive mechanism unit 13, an imaging visual field control unit 14, an image processing unit 15, a storage unit 16, a timer 17, and a communication unit 18. I have. The control unit 11 controls the operation of each part of the main body.

  The imaging unit 12 outputs a frame image obtained by imaging the imaging field (imaging area) about 30 frames per second. The imaging unit 12 is attached to a pan head (not shown) that rotates individually in the pan direction and the tilt direction. The pan direction and the tilt direction are orthogonal to each other. The imaging unit 12 includes an optical system driving unit (not shown) that drives the imaging optical system, and can change the imaging magnification Zoom.

  The drive mechanism unit 13 includes a drive source such as a motor that rotates the pan head to which the imaging unit 12 is attached in the pan direction and the tilt direction. In addition, a sensor that detects a rotation angle θ applied to the pan direction of the pan head and a rotation angle φ applied to the tilt direction is provided.

  The imaging view control unit 14 instructs the imaging unit 12 on the imaging magnification. The imaging unit 12 changes the imaging magnification Zoom according to this instruction. In addition, the imaging visual field control unit 14 instructs the drive mechanism unit 13 about the rotation angle θ in the pan direction and the rotation angle φ in the tilt direction of the pan head on which the imaging unit 12 is attached. In accordance with this instruction, the drive mechanism unit 13 changes the rotation angle θ applied in the pan direction and the rotation angle φ applied in the tilt direction of the camera head to which the imaging unit 12 is attached.

  The imaging field of view of the imaging unit 12 changes in accordance with changes in the rotation angle θ in the pan direction of the camera platform, the rotation angle φ in the tilt direction of the camera platform, and the imaging magnification Zoom. As shown in FIG. 3, the monitoring camera terminal 1 has a monitoring target area. This monitoring target area is a range in which imaging can be performed by changing the imaging field of view of the imaging unit 12.

  In addition, the image processing unit 15 processes the frame image captured by the imaging unit 12, extracts a person being imaged, and assigns an ID to the extracted person. This ID is a unique value that can identify a person. In addition, the image processing unit 15 is supplied with outputs of sensors that detect a rotation angle θ applied to the pan head of the pan head to which the imaging unit 12 is attached and a rotation angle φ applied to the tilt direction. That is, the image processing unit 15 obtains the rotation angle θ applied in the pan direction and the rotation angle φ applied in the tilt direction of the pan head to which the imaging unit 12 is attached, from the output of the sensor. Further, the image processing unit 15 obtains an imaging magnification Zoom of the imaging unit 12 based on a signal related to the imaging magnification input from the imaging unit 12. The image processing unit 15 uses the rotation angle θ in the pan direction of the pan head, the rotation angle φ in the tilt direction, and the imaging magnification Zoom, and the imaging field of view of the imaging unit 12, that is, the position of the imaging area in the monitoring target area, Can be obtained. Therefore, the image processing unit 15 can convert the position of the person on the frame image captured by the imaging unit 12 into the position in the monitoring target area. The image processing unit 15 instructs the imaging field controller 14 to determine the imaging field of view of the imaging unit 12 according to the movement of the person being tracked.

  The image processing unit 15 is configured to extract and track a person being imaged using, for example, a spatio-temporal MRF (Markov Random Field) model. As is well known, the spatiotemporal MRF model is an extension of the MRF model as a spatiotemporal model, focusing on the correlation in the time axis direction of the spatiotemporal image. This spatio-temporal MRF model divides an area into blocks of several pixels × several pixels (for example, 8 pixels × 8 pixels) for a frame image to be processed, and each block between temporally continuous frame images. This is a model that defines the correlation in the time axis direction with reference to the motion vector.

  The storage unit 16 stores an operation program for operating the main body, setting data used during operation, processing data generated during operation, and the like. The timer 17 measures the current time. The communication unit 18 controls data communication with other surveillance camera terminals 1.

  This wide-area monitoring system is a system for tracking a person such as a suspicious person (hereinafter referred to as a tracking target person) who has taken a specific action. Each monitoring camera terminal 1 is assigned a monitoring target area as described above. Further, as shown in FIG. 4, two adjacent monitoring camera terminals 1 </ b> A and 1 </ b> B partially overlap the monitoring target area. FIG. 4 illustrates the monitoring target areas for the two adjacent monitoring camera terminals 1A and 1B. However, in the combination of the other two adjacent monitoring camera terminals 1, a part of the monitoring target area overlaps. Yes. This overlapping area is a delivery area for delivering the tracking target person from one surveillance camera terminal 1A (or 1B) to the other surveillance camera terminal 1B (or 1A). For example, when the tracking target person tracked by the monitoring camera terminal 1A enters the monitoring target area of the monitoring camera terminal 1B through the transfer area with the monitoring camera terminal 1B, the monitoring camera terminal 1B This is an area for identifying a tracking target person and taking over the tracking target person from the monitoring camera terminal 1A.

  The surveillance camera terminal 1 captures an imaging field of view of the imaging unit 12 (a rotation angle θ and a tilt direction in the pan direction) when the tracking target person is transferred to and from the surveillance camera terminal 1 for each adjacent surveillance camera terminal 1. Is stored in the storage unit 16. The imaging field of view of the imaging unit 12 when delivering the tracking target person includes a delivery area with the counterpart monitoring camera terminal 1 that delivers the tracking target person.

  In addition, each monitoring camera terminal 1 has, for each adjacent monitoring camera terminal 1, a two-dimensional coordinate system of a frame image obtained by imaging the transfer area by the imaging unit 12 of its own terminal, and an imaging unit of the adjacent counterpart monitoring camera terminal 1 12 stores coordinate conversion information indicating a relative positional relationship with the two-dimensional coordinate system of the frame image obtained by imaging the transfer area in the storage unit 16. The coordinate conversion information is obtained by tracking the two-dimensional coordinate system of the frame image captured in the imaging field when the imaging unit 12 of the own terminal delivers the tracking target and the imaging unit 12 of the adjacent counterpart monitoring camera terminal 1 to be tracked. Information for projective transformation of the two-dimensional coordinate system of the frame image captured in the imaging field of view when the person is handed over to a common coordinate system. Here, a first coordinate conversion parameter and a second coordinate conversion parameter shown below are stored in the storage unit 16 as the coordinate conversion information. The first coordinate transformation parameter is obtained by the imaging unit 12 of the adjacent counterpart camera terminal 1 using the two-dimensional coordinate system of the frame image captured in the imaging field when the imaging unit 12 of the own terminal delivers the tracking target person. This is a parameter for projective transformation to a two-dimensional coordinate system of a frame image captured in an imaging field of view when a tracking target person is delivered. Further, the second coordinate conversion parameter is obtained by using the two-dimensional coordinate system of the frame image captured in the imaging field when the imaging unit 12 of the adjacent counterpart monitoring camera terminal 1 delivers the tracking target person as the imaging unit of the own terminal. 12 is a parameter for projective transformation to a two-dimensional coordinate system of a frame image captured in the imaging field of view when the tracking target person is delivered.

  Note that the coordinate conversion information may be only one of the first coordinate conversion parameter and the second coordinate conversion parameter.

  Here, the first coordinate conversion parameter and the second coordinate conversion parameter will be described. The first coordinate conversion parameter and the second coordinate conversion parameter are values calculated using a frame image actually captured when the surveillance camera terminal 1 is installed.

First, when the installation of the monitoring camera terminal 1 is completed, four points are marked on the floor surface in the transfer area with the adjacent counterpart monitoring camera terminal 1 using a tape or the like. And the frame image imaged with the imaging visual field when the imaging part 12 of an own terminal delivers a tracking subject is processed, and the coordinate position (x, y) of four points marked on this frame image is detected. Similarly, the coordinate positions (X, Y) of the four points marked on the frame image captured in the imaging field when the imaging unit 12 of the adjacent counterpart monitoring camera terminal 1 delivers the tracking target person are displayed on the counterpart side. Obtain from the terminal. And for each marked point, its coordinate position is
X = (a1x + b1y + c1) / (a0x + b0y + 1)
Y = (a2x + b2y + c2) / (a0x + b0y + 1)
To obtain an 8-ary simultaneous equation. The eight counts a0, b0, a1, b1, c1, a2, b2, and c2, which are the solutions of the 8-ary simultaneous equations, are the first coordinate conversion parameters with the adjacent counterpart monitoring camera terminal 1. is there. The surveillance camera terminal 1 stores the first coordinate conversion parameter in the storage unit 16.

Similarly, for each marked point, its coordinate position is
x = (A1X + B1Y + C1) / (A0X + B0Y + 1)
y = (A2X + B2Y + C2) / (A0X + B0Y + 1)
To obtain an 8-ary simultaneous equation. Eight counts of A0, B0, A1, B1, C1, A2, B2, and C2, which are the solutions of the 8-ary simultaneous equations, are the second coordinate conversion parameters with the adjacent counterpart monitoring camera terminal 1. is there. The surveillance camera terminal 1 stores the second coordinate conversion parameter in the storage unit 16.

  For identification of a person located in the transfer area, the coordinate position on the frame image is acquired for each person imaged in the transfer area of the frame image captured by the terminal. Further, the coordinate position on the frame image is acquired from the counterpart terminal for each person imaged in the frame image transfer area captured by the counterpart terminal. Also, a combination pattern is created in which the person located in the delivery area imaged by the terminal is associated with the person located in the delivery area imaged by the partner terminal on a one-to-one basis. The number of combination patterns created here is, for example, two if there are two persons located in the delivery area, and 6 if there are three persons located in the delivery area. Street.

  Moreover, the surveillance camera terminal 1 converts the coordinate position of the person into the coordinate system of the counterpart terminal using the first coordinate conversion parameter for each person located in the transfer area captured by the terminal. The surveillance camera terminal 1 calculates the first distance energy that is the sum of the distances between the corresponding persons in the coordinate system of the counterpart terminal for each person combination pattern. Moreover, the surveillance camera terminal 1 converts the coordinate position of the person into the coordinate system of the own terminal using the second coordinate conversion parameter for each person located in the transfer area imaged by the counterpart terminal. The surveillance camera terminal 1 calculates the second distance energy that is the sum of the distances between corresponding persons in the coordinate system of the terminal for each person combination pattern.

  And the surveillance camera terminal 1 is a person located in the delivery area with a combination pattern having the smallest sum of the first distance energy and the second distance energy among the combinations of persons located in the delivery area. Is determined to be an appropriate association. Therefore, if the tracking target person is located in the delivery area, the tracking target person can be identified.

  Next, the operation of the monitoring camera terminal 1 will be described. FIG. 5 is a flowchart showing the operation of the surveillance camera terminal 1. The monitoring camera terminal 1 starts a search process related to searching for a tracking target person in the monitoring target area (S1). At this time, the monitoring camera terminal 1 does not track the person to be tracked (does not execute the tracking process described later). The monitoring camera terminal 1 waits for a tracking target person to be searched for in the monitoring target area (S2) or to receive a tracking target person transfer request from the adjacent monitoring camera terminal 1 (S3).

  The search process starting at S1 changes the imaging field of the imaging unit 12 every certain time (several seconds). Specifically, the imaging visual field control unit 14 rotates the rotation angle θ in the pan direction and the rotation in the tilt direction of the pan head to which the imaging unit 12 is attached based on a predetermined condition at regular intervals. The moving angle φ is instructed to the drive mechanism unit 13. For example, this condition is set so that the imaging field of view of the imaging unit 12 scans the monitoring target area. The imaging magnification Zoom is a predetermined magnification.

  The image processing unit 15 processes the frame image captured by the imaging unit 12 to extract the person being imaged, and gives an ID to the extracted person. At this time, the image processing unit 15 does not assign an ID to a person who has already been assigned an ID. Further, the image processing unit 15 creates an object map in which the ID and the position in the monitoring target area are associated for each extracted person. This object map is given the time stamped by the timer 17 at the time of creation as a time stamp. The image processing unit 15 analyzes the behavior of each person to whom an ID is assigned, using an object map that is temporally continuous. If there is a person whose action is unique, the person is detected as a tracking target person. In addition, when a face image of a person requiring attention is registered and a person requiring attention is detected by collation with the face image of the person captured by the imaging unit 12, the person requiring attention is detected as a tracking target person. You may comprise.

  When the tracking target person is searched, the monitoring camera terminal 1 starts tracking processing (S4). FIG. 6 is a flowchart showing the tracking process. The image processing unit 15 captures the frame image captured by the imaging unit 12 (S11), processes the frame image, and captures the imaging field of view (rotation in the pan direction of the pan head) where the tracking target person is the center of the imaging unit 12. The angle θ and the rotation angle φ in the tilt direction are calculated (S12). At this time, the imaging magnification Zoom of the imaging unit 12 is a predetermined magnification.

  The surveillance camera terminal 1 matches the imaging field of the imaging unit 12 with the imaging field calculated in S12 (S13). That is, the rotation angle θ in the pan direction of the pan head and the rotation angle φ in the tilt direction are matched with the angle calculated in S12. Specifically, the image processing unit 15 notifies the imaging visual field control unit 14 of the rotation angle θ applied in the pan direction of the pan head and the rotation angle φ applied in the tilt direction calculated here. Based on this notification, the imaging visual field control unit 14 changes the rotation angle θ applied in the pan direction of the pan head by the drive mechanism unit 13 and the rotation angle φ applied in the tilt direction.

  The monitoring camera terminal 1 determines whether or not the tracking target person has moved to the vicinity of a delivery area with another adjacent monitoring camera terminal 1 (S14). If the surveillance camera terminal 1 determines that the tracking target person has not moved to the vicinity of the delivery area with the other surveillance camera terminal 1 adjacent thereto, the surveillance camera terminal 1 returns to S11 and repeats the above-described processing.

  As shown in FIG. 7, the surveillance camera terminal 1 tracks the tracking target person X while capturing the tracking target person X at the approximate center of the imaging field of view of the imaging unit 12 by repeating the processes shown in S11 to S14. be able to. In this tracking process, the image processing unit 15 also creates an object map that associates the ID with the position in the monitoring target area for the tracking target person. Therefore, by using this object map, a movement vector relating to the moving direction and moving speed of the tracking target person can be obtained.

When the monitoring camera terminal 1 determines that the tracking target person has moved around the transfer area with the other adjacent monitoring camera terminal 1, the tracking target person is transferred to the adjacent other monitoring camera terminal 1. A request is made (S15). In S14, for example, the tracking target person is adjacent based on the imaging field of view of the imaging unit 12 when the tracking target person is transferred to and from another adjacent monitoring camera terminal 1, and the current imaging field of view. It is determined whether or not it is moving to the vicinity of the transfer area with the other monitoring camera terminal 1 that performs. Specifically, the imaging field of view of the imaging unit 12 when the tracking target person is transferred to and from another adjacent monitoring camera terminal 1 is set to the rotation angle (θ1) applied to the pan direction of the pan head and the tilt. The rotation angle (φ1) applied to the direction, the imaging magnification (z1), and the imaging field of view of the current imaging unit 12 is the rotation angle (θt) applied to the pan direction of the pan head and the rotation angle applied to the tilt direction. (Φt), when the imaging magnification (zt),
(a): φ1−V ≦ φt ≦ φ1 + V (V is a vertical angle of view when the imaging magnification is z1)
(b): θ1−H ≦ θt ≦ θ1 + H / 2 (H is a horizontal angle of view when the imaging magnification is z1)
When both of these conditions are satisfied, it is determined that the tracking target person has moved to the vicinity of the delivery area with the other monitoring camera terminal 1 adjacent thereto.

  In addition, when an appropriate mark is printed on the floor surface outside the transfer area around the transfer area, and the image processing unit 15 detects the mark when the captured image of the imaging unit 12 is processed, You may make it determine with the tracking object person having moved to the delivery area periphery with the other surveillance camera terminal 1 which adjoins. Further, instead of the mark, a structure or the like provided outside the transfer area may be used around the transfer area. Further, the determination may be made based on the position of the tracking target person being tracked in the monitoring target area.

  When the surveillance camera terminal 1 makes a delivery request for the tracking target person in S15, the imaging magnification Zoom is changed to the above-described z1 (imaging magnification at the time of delivery) (S16). The image processing unit 15 captures and processes the frame image captured by the imaging unit 12 (S17), and determines whether the tracking target person is out of frame when the imaging field of view of the imaging unit 12 is transferred to the imaging field of view. Determine (S18). When the surveillance camera terminal 1 determines that the tracking target person is out of frame in S18, the imaging field of view (the rotation angle (θ) applied to the pan direction of the pan head and the rotation angle (θ) applied to the tilt direction ( φ)) is calculated (S19). In S19, as the imaging field, the imaging field centered on the person to be tracked may be calculated. However, preferably, the field of view to be imaged near the imaging field at the time of delivery is calculated by shifting the person to be tracked from the center. . The surveillance camera terminal 1 matches the imaging field of the imaging unit 12 with the imaging field calculated in S19 (S20), and returns to S17.

  If the surveillance camera terminal 1 determines that the tracking target person does not frame out in S18, the surveillance camera terminal 1 determines the imaging field of view of the imaging unit 12 as the imaging field of view stored in the storage unit 16 (S21). The surveillance camera terminal 1 adjusts the imaging field of view of the imaging unit 12 to the imaging field of view at the time of delivery (S22).

  As described above, when the tracking target person is not located in the vicinity of the transfer area with another adjacent monitoring camera terminal 1, the monitoring camera terminal 1 is based on the tracking target person (the tracking target person is in the imaging field of view). The imaging visual field of the imaging unit 12 is changed so as to be in the center. On the other hand, when the person to be tracked is located in the vicinity of the transfer area with another monitoring camera terminal 1 adjacent thereto, the imaging field of view of the imaging unit 12 is changed with reference to the imaging field of view at the time of delivery. Therefore, when the tracking target person enters the delivery area, the imaging field of the imaging unit 12 is the imaging field at the time of delivery.

  The adjacent surveillance camera terminal 1 that has received the tracking target person delivery request made in S15 described above starts the handover process (S5). This adjacent monitoring camera terminal 1 takes over the tracking of the tracking target person. Hereinafter, another monitoring camera terminal 1 that takes over the tracking of the tracking target person is referred to as a takeover-side monitoring camera terminal 1. The surveillance camera terminal 1 on the side that has transmitted the tracking target person's delivery request in S15 is referred to as delivery side surveillance camera terminal 1.

  FIG. 8 is a flowchart showing a delivery process performed by the takeover-side monitoring camera terminal. The takeover-side monitoring camera terminal 1 matches the imaging field of the imaging unit 12 with the imaging field when the tracking target person is transferred to and from the adjacent monitoring camera terminal 1 that has transmitted the transfer request received this time (S31). ). That is, when the takeover-side monitoring camera terminal 1 receives the delivery request, at that time, the imaging field of view of the imaging unit 12 is changed to the imaging field of view when the tracking target person is delivered to the delivery-side monitoring camera terminal 1. Match.

  The takeover-side monitoring camera terminal 1 waits for a synchronization signal from the delivery-side monitoring camera terminal 1 (S32).

  The transfer-side monitoring camera terminal 1 waits for the tracking target person to enter the transfer area when matched with the imaging field of view when the tracking target person is transferred with the takeover-side monitoring camera terminal 1 in S22 (S23). . When the tracking target person enters the delivery area, the delivery monitoring camera terminal 1 transmits a synchronization signal to the takeover monitoring camera terminal 1 (S24). This synchronization signal may notify the time or simply notify the reference timing.

  The monitoring camera terminal 1 that delivers the tracking target person and the monitoring camera terminal 1 that takes over the tracking target person captures the frame image captured by the imaging unit 12 at a timing based on the synchronization signal (S25, S33). The takeover-side monitoring camera terminal 1 identifies the tracking target person being imaged with the monitoring camera terminal 1 on the side of transferring the tracking target person based on the captured image obtained by imaging the transfer area (S26, S34). ). The tracking target person may be identified by a technique using the first distance energy and the second distance energy described above.

  The takeover-side monitoring camera terminal 1 ends this takeover process and starts the tracking process in S4 described above. Moreover, the delivery-side monitoring camera terminal 1 ends the tracking process in S4 and returns to S1.

  As described above, when the tracking target person enters the delivery area, the delivery monitoring camera terminal 1 and the takeover monitoring camera terminal 1 have the imaging field of view of the imaging unit 12 set at the time of delivery set in advance. ing. That is, it does not take time for the surveillance camera terminal 1 to change the imaging field of view to the imaging field of view when the tracking subject is delivered after the tracking subject enters the delivery area. Therefore, it is possible to suppress losing sight of the tracking target when the tracking target person being tracked is delivered to another monitoring camera terminal 1.

DESCRIPTION OF SYMBOLS 1 (1A-1H) ... Surveillance camera terminal 11 ... Control part 12 ... Imaging part 13 ... Drive mechanism part 14 ... Imaging visual field control part 15 ... Image processing part 16 ... Memory | storage part 17 ... Timer 18 ... Communication part

Claims (5)

An imaging means for outputting a frame image obtained by imaging the imaging field;
An imaging visual field control means for changing an imaging visual field of the imaging means within a monitoring target area;
A tracking target extracting unit that processes a frame image captured by the imaging unit and extracts a tracking target being imaged;
A tracking unit that detects the position of the tracking target in the monitoring target area based on the position on the frame image of the tracking target extracted by the tracking target extraction unit and the imaging field of view of the imaging unit, and tracks the tracking target; With
In the surveillance camera terminal, the imaging visual field control means changes an imaging visual field of the imaging means according to a position in the monitoring target area of the tracking target tracked by the tracking means.
An imaging field of view storage means for storing an imaging field of view when the tracking target is transferred for each of the other surveillance camera terminals that perform the transfer of the tracking target;
Detecting means for detecting whether or not the tracking target being tracked by the tracking means has moved to the vicinity of a delivery area that delivers the tracking target to or from another surveillance camera terminal ;
When the detection means detects that the tracking target tracked by the tracking means has moved to the vicinity of a delivery area with another monitoring camera terminal, the imaging visual field control means captures the imaging visual field of the imaging means. A monitoring camera terminal that matches the imaging field of view when the tracking target is transferred to and from the other monitoring camera terminal stored in the field of view storage means.   When the imaging visual field control means detects that the tracking target tracked by the tracking means has moved to the vicinity of a delivery area with another monitoring camera terminal, the imaging visual field control means captures the tracking target by the imaging means. The surveillance camera terminal according to claim 1, wherein an imaging field of view of the imaging unit is changed while being within a field of view, and is matched with an imaging field when a tracking target is delivered.   The monitoring camera terminal according to claim 1, further comprising a synchronization unit that synchronizes an imaging timing of the imaging unit with another monitoring camera terminal that delivers a tracking target.   When it is detected by the detection means that the tracking target being tracked by the tracking means has moved to the vicinity of the delivery area with another monitoring camera terminal, another monitoring camera terminal that delivers the tracking target The surveillance camera terminal according to claim 1, further comprising a delivery request notification means for making a delivery request.   When the imaging visual field control means receives the transfer request from another monitoring camera terminal, the imaging visual field control means tracks the imaging visual field of the imaging means with the other monitoring camera terminal stored in the imaging visual field storage means. The surveillance camera terminal according to claim 4, wherein the surveillance camera terminal is adapted to an imaging field of view when the object is delivered.

Images